Category
AI Development Articles
Page 14 of 41. Deep dives into AI-assisted and agentic development. Coding agents, frontier model releases, SDKs, prompting patterns, and the engineering workflows behind building production software with AI.
Page 14 of 41
The newest AI Development guides and analysis
Four dated instances since June 2025 of a frontier lab restricting model access, three of them involving a coding tool. Nothing was cut off overnight.
#model-access#vendor-risk+6 more
2026-08-28
Read Article
Z.ai published GLM-5.3's 753B weights on August 28 under a bespoke licence, two days after shipping GLM-5.3-Flash under plain MIT. The clause that differs.
#glm-5-3#z-ai+5 more
2026-08-28
Read Article
OpenAI says it will wind down the contract supplying its models to Cursor, with a proposed cutoff of November 12, 2026. What BYOK does not cover.
#openai#cursor+5 more
2026-08-28
Read Article
In the 2025-26 record we checked, two labs gave a public reason before holding back open weights. What a stated delay tells a buyer, and what it does not.
#open-weights#model-releases+5 more
2026-08-28
Read Article
Clip length and resolution each collapse distinct mechanisms coverage flattens into one number. A reference for reading AI video spec sheets against the docs.
#ai video#video generation+5 more
2026-08-27
Read Article
fal says H3 Max renders five seconds of video in under three. The claim is the vendor's own, and the tracker it cites backs the quality half only in part.
#fal#minimax h3+5 more
2026-08-27
Read Article
Google's Omni 1.1 Flash chains 10-second extensions up to 40 seconds and documents 1080p and 4K as upscales. What the reported $0.03/s draft tier buys.
#gemini omni 1.1 flash#ai video generation+5 more
2026-08-27
Read Article
Text input has one unit. Image input has several conversion rules, and some vendors publish none. An input-side reference that names what it will not normalize.
#multimodal#ai-pricing+4 more
2026-08-26
Read Article
OpenRouter documents what its rankings count and what they exclude. A source-pinned inventory of what a usage chart measures, and what it cannot tell you.
#openrouter#usage-data+4 more
2026-08-26
Read Article
Z.ai named its stealth model on August 26 and shipped MIT weights the same day. What the identity actually changes for an endpoint already in production.
#glm-5-3-flash#ox-alpha+5 more
2026-08-26
Read Article
Alibaba open-weighted Qwen3.8-Flash-Next on August 26. The hosted Qwen3.8-Flash is a documented, different artifact — licence, context and tools all diverge.
#qwen3-8-flash-next#qwen+4 more
2026-08-26
Read Article
A reveal is not reassurance — it starts a re-verification job. The checks that only become possible, or only become urgent, the day anonymity ends.
#stealth-models#model-evaluation+4 more
2026-08-26
Read Article
AI video is quoted in four incompatible units. One formula puts five vendors' published rates into a single comparable column, and excludes the two it cannot.
#ai-video-pricing#cost-per-second+5 more
2026-08-25
Read Article
An anonymous model's benchmark score and its identity are different products. What stealth-listing terms disclose, and what no eval can tell you.
#anonymous-model-evaluation#openrouter-stealth+5 more
2026-08-25
Read Article
Twelve vendor surfaces, one question: what is documented at the metering boundary? Mostly a hard stop with an HTTP error, not the quiet degrade teams assume.
#ai-spend-caps#rate-limits+5 more
2026-08-25
Read Article
A retry wrapper that cannot tell a spend-cap 429 from a rate-limit 429 burns real money for zero work. Cache math, retry burn and checkpoint economics.
#agent-cost-budgeting#retry-burn+5 more
2026-08-25
Read Article
M5 Ultra scales to 512GB of unified memory at 1.2TB/s, but that configuration has no published price and arrives in late October. What actually fits.
#m5-ultra#mac-studio+5 more
2026-08-25
Read Article
What nine AI coding CLIs do before you choose anything: trust prompts, telemetry defaults, and mid-task keystrokes, pinned to sources read on August 24, 2026.
#ai-cli#developer-tooling+6 more
2026-08-24
Read Article
Agent-written tables can state a correct formula and still print cells that break it. Why fact-checking misses this, and a recompute pass that catches it.
#ai-quality-assurance#agentic-workflows+5 more
2026-08-24
Read Article
Identical dollar-per-million pricing does not mean identical cost: tokenizers split the same text into different counts. A vocabulary reference table.
#tokenizers#llm-pricing+5 more
2026-08-24
Read Article
A dated ledger of 27 MCP security entries — 25 incidents plus 2 protocol revisions — April 2025 to August 2026: component, defect class, route, patch status.
#mcp-security#model-context-protocol+5 more
2026-08-24
Read Article
A census of 15 rows across 14 agent frameworks, scored against five SSRF controls from primary sources. Two default fetch paths re-validate every redirect hop.
#ssrf#agent-frameworks+4 more
2026-08-23
Read Article
Nine logged August runs, 94 posts, measured from our own build records: what first-pass verify actually passes, and which defect classes keep coming back.
#agentic-workflows#content-operations+4 more
2026-08-23
Read Article
Higgsfield's video engine now runs inside Grok Bot's tool loop, billed per call. The approval framework does not name metered generation as a gated action.
#grok-bot#higgsfield+4 more
2026-08-23
Read Article
Digital Applied newsletter
Deep dives on AI, marketing and development.
Practical guides and fresh insights by email. No recycled takes.